paper-with-me

홈 › Papers

Disentangle, align and fuse for multimodal and semi-supervised image segmentation

2019-11-11 · Agisilaos Chartsias, Giorgos Papanastasiou, Chengjia Wang, Scott Semple, David E. Newby, Rohan Dharmakumar, Sotirios A. Tsaftaris

Magnetic resonance (MR) protocols rely on several sequences to assess pathology and organ status properly. Despite advances in image analysis, we tend to treat each sequence, here termed modality, in isolation. Taking advantage of the common information shared between modalities (an organ's anatomy) is beneficial for multi-modality processing and learning. However, we must overcome inherent anatomical misregistrations and disparities in signal intensity across the modalities to obtain this benefit. We present a method that offers improved segmentation accuracy of the modality of interest (over a single input model), by learning to leverage information present in other modalities, even if few (semi-supervised) or no (unsupervised) annotations are available for this specific modality. Core to our method is learning a disentangled decomposition into anatomical and imaging factors. Shared anatomical factors from the different inputs are jointly processed and fused to extract more accurate segmentation masks. Image misregistrations are corrected with a Spatial Transformer Network, which non-linearly aligns the anatomical factors. The imaging factor captures signal intensity characteristics across different modality data and is used for image reconstruction, enabling semi-supervised learning. Temporal and slice pairing between inputs are learned dynamically. We demonstrate applications in Late Gadolinium Enhanced (LGE) and Blood Oxygenation Level Dependent (BOLD) cardiac segmentation, as well as in T2 abdominal segmentation. Code is available at https://github.com/vios-s/multimodal_segmentation.

📄 PDF Abstract BibTeX arXiv:1911.04417

Code (2)

agis85/multimodal_segmentation 공식 구현 tf
vios-s/multimodal_segmentation 공식 구현 tf

Tasks

AnatomyCardiac SegmentationImage ReconstructionImage SegmentationSegmentationSemantic SegmentationZero-Shot Learning

Methods 이 논문이 사용한 방법론

Linear Layer A Linear Layer is a projection $\mathbf{XW + b}$.
Absolute Position Encodings Absolute Position Encodings are a type of position embeddings for [Transformer-based models] where positional encodings are…
Position-Wise Feed-Forward Layer 설명 없음
Spatial Transformer A Spatial Transformer is an image model block that explicitly allows the spatial manipulation of data within a [convolutional neural…
Residual Connection 설명 없음
BPE Byte Pair Encoding, or BPE, is a subword segmentation algorithm that encodes rare and unknown words as sequences of subword units. The intuition is that various word…
Dense Connections Dense Connections, or Fully Connected Connections, are a type of layer in a deep neural network that use a linear operation where every input is connected to every output…
Label Smoothing Label Smoothing is a regularization technique that introduces noise for the labels. This accounts for the fact that datasets may have mistakes in them, so maximizing the…

Similar Papers 제목 키워드 기반

DisenSemi: Semi-supervised Graph Classification via Disentangled Representation Learning

2024-07-19 · Yifan Wang, Xiao Luo, Chong Chen, Xian-Sheng Hua 외

Graph classification is a critical task in numerous multimedia applications, where graphs are employed to represent diverse types of multimedia data, including images, videos, and social networks. Nevertheless, in real-w…

ClassificationGraph ClassificationRepresentation Learning

STiL: Semi-supervised Tabular-Image Learning for Comprehensive Task-Relevant Information Exploration in Multimodal Classification

2025-03-08 · CVPR 2025 1 · Siyi Du, Xinzhe Luo, Declan P. O'Regan, Chen Qin

Multimodal image-tabular learning is gaining attention, yet it faces challenges due to limited labeled data. While earlier work has applied self-supervised learning (SSL) to unlabeled data, its task-agnostic nature often…

DisentanglementPseudo LabelSelf-Supervised Learning

Data-Efficient Multimodal Fusion on a Single GPU

2023-12-15 · CVPR 2024 1 · Noël Vouitsis, Zhaoyan Liu, Satya Krishna Gorti, Valentin Villecroze 외

The goal of multimodal alignment is to learn a single latent space that is shared between multimodal inputs. The most powerful models in this space have been trained using massive datasets of paired inputs and large-scal…

GPUImage RetrievalRetrievalText Retrieval

Towards Multimodal Domain Generalization with Few Labels

2026-02-26 · Hongzhao Li, Hao Dong, Hualei Wan, Shupan Li 외 arxiv

Multimodal models ideally should generalize to unseen domains while remaining data-efficient to reduce annotation costs. To this end, we introduce and study a new problem, Semi-Supervised Multimodal Domain Generalization…

Domain Generalization

Mutual Information-based Representations Disentanglement for Unaligned Multimodal Language Sequences

2024-09-19 · Fan Qian, Jiqing Han, Jianchen Li, Yongjun He 외

The key challenge in unaligned multimodal language sequences lies in effectively integrating information from various modalities to obtain a refined multimodal joint representation. Recently, the disentangle and fuse met…

Disentanglement